mlsanityData to 7 Oct 2026

MaskCD: Mitigating LVLM Hallucinations by Image Head Masked Contrastive Decoding

arXiv 2510.02790 ↗First posted 3 Oct 2025cs.CV cs.AI cs.CLcited by 6

On the map: Multimodal LLMs / vision-language models → Hallucination mitigation in LVLMs

Abstract (arXiv)

Large vision-language models (LVLMs) have shown remarkable performance in visual-language understanding for downstream multimodal tasks. While their capabilities are improving, problems emerge simultaneously. Among those problems, the hallucinations have attracted much attention, which stands for the phenomenon where LVLMs generate contradictory content to their input visual and text contents. Many approaches have been proposed to deal with this issue, such as contrastive decoding and attention manipulation. However, contrastive decoding methods struggle in constructing appropriate contrastive samples, and attention manipulation methods are highly sensitive, lacking stability. In this work, we propose image head Masked Contrastive Decoding (MaskCD). Our approach utilizes the "image heads" in LVLMs, masking them to construct contrastive samples for contrastive decoding. We evaluated MaskCD on LLaVA-1.5-7b and Qwen-VL-7b, using various benchmarks such as CHAIR, POPE, AMBER and MME. The results demonstrate that MaskCD effectively alleviates the phenomenon of hallucinations and retains the general capabilities of LVLMs. Corresponding resources could be found at: https://github.com/Deng-Jingyuan/MaskCD .

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Placed in Hallucination mitigation in LVLMs, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 20 of its 31 references that are in the map. First posted on arXiv 3 Oct 2025.

Builds on

20 of 31 references.

Closest ancestors · 10

Same direction, newest first

  1. 2025Attention Reallocation: Towards Zero-cost and Controllable Hallucination Mitigation of MLLMs11 Mar
  2. 2024Paying More Attention to Image: A Training-Free Method for Alleviating Hallucination in LVLMs31 Jul
  3. 2024Mitigating Hallucinations in Large Vision-Language Models with Instruction Contrastive Decoding27 Mar
  4. 2024Multi-Modal Hallucination Control by Visual Information Grounding20 Mar
  5. 2024IBD: Alleviating Hallucinations in Large Vision-Language Models via Image-Biased Decoding28 Feb
  6. 2023OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation29 Nov
  7. 2023Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding28 Nov
  8. 2023Volcano: Mitigating Multimodal Hallucination through Self-Feedback Guided Revision13 Nov
  9. 2023CIEM: Contrastive Instruction Evaluation Method for Better Instruction Tuning5 Sep
  10. 2023Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning26 Jun

Other references · 10

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  5. 2023Improved Baselines with Visual Instruction Tuningcited by 4,362
  6. 2023InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuningcited by 2,855
  7. 2023Efficient Streaming Language Models with Attention Sinkscited by 2,115
  8. 2023mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaborationcited by 545
  9. 2023What's "up" with vision-language models? Investigating their struggle with spatial reasoningcited by 245
  10. 2023DRESS: Instructing Large Vision-Language Models to Align and Interact with Humans via Natural Language Feedbackcited by 99

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 6.

6 papers.

  1. 2026Vision-Language Introspection: Mitigating Overconfident Hallucinations in MLLMs via Interpretable Bi-Causal Steeringcited by 8
  2. 2026Mitigating Hallucinations in Large Vision-Language Models via Causal Route Gatingcited by 2
  3. 2026Gaze Heads: How VLMs Look at What They Describecited by 2
  4. 2026Do We Really Need External Tools to Mitigate Hallucinations? SIRA: Shared-Prefix Internal Reconstruction of Attributioncited by 1
  5. 2026Risk-aware Selective Prompting for Hallucination Mitigation in Large Vision-Language Modelscited by 1
  6. 2026YARD: Y-Architecture Register Decoding for Efficient Hallucination Mitigation in Large Vision-Language Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Mitigating Hallucinations in Large Vision-Language Models (LVLMs) via Language-Contrastive Decoding (LCD)
  2. 2024Delve into Visual Contrastive Decoding for Hallucination Mitigation of Large Vision-Language Models
  3. 2025Mitigating Hallucination in Multimodal LLMs with Layer Contrastive Decoding
  4. 2025AVCD: Mitigating Hallucinations in Audio-Visual Large Language Models through Contrastive Decoding
  5. 2026SDCD: Structure-Disrupted Contrastive Decoding for Mitigating Hallucinations in Large Vision-Language Models
  6. 2024CATCH: Complementary Adaptive Token-level Contrastive Decoding to Mitigate Hallucinations in LVLMs
  7. 2025Mitigating Hallucinations in Large Vision-Language Models with Internal Fact-based Contrastive Decoding
  8. 2025Efficient Contrastive Decoding with Probabilistic Hallucination Detection - Mitigating Hallucinations in Large Vision Language Models -